A prosodic Hidden Markov model (HMM) based modality recognizer has been developed, which, after supra-segmental acoustic pre-processing, can perform clause and sentence boundary detection and modality (sentence type) recognition. This modality recognizer is adapted to carry out automatic evaluation of the intonation of the produced utterances in a speech training system for hearing-impaired persons or foreign language learners. The system is evaluated on utterances from normally-speaking persons and tested with speech-impaired (due to hearing problems) persons. To allow a deeper analysis, the automatic classification of the intonation is compared to subjective listening tests.
Cite as: Szaszák, G., Sztahó, D., Vicsi, K. (2009) Automatic intonation classification for speech training systems. Proc. Interspeech 2009, 1899-1902, doi: 10.21437/Interspeech.2009-550
@inproceedings{szaszak09_interspeech,
author={György Szaszák and Dávid Sztahó and Klára Vicsi},
title={{Automatic intonation classification for speech training systems}},
year=2009,
booktitle={Proc. Interspeech 2009},
pages={1899--1902},
doi={10.21437/Interspeech.2009-550}
}